Algolux recently introduced its NaturalIQ, an artificial intelligence (AI) approach that automates the tedious task of subjective camera tuning by learning image quality (IQ) preferences from users’ natural image datasets. The company has created what it calls the industry’s first automated approach to optimal IQ tuning by applying unique machine learning solvers and objective metrics, or KPIs, through its CRISP-ML software platform and methodology. This approach proves to significantly reduce tuning time and cost, while improving scalability.
NaturalIQ allows camera teams to tune against a dataset of their preferred natural images that represents the image quality outcome they desire. This image dataset can be created with photo editing tools or captured with a camera of choice. Once a meaningful image dataset is collected, the images are displayed and captured by the camera configuration being tuned. NaturalIQ iteratively analyzes the camera output to determine how close the camera’s tuning parameter settings are to the goal defined by the image dataset and searches the parameter space to find the best settings (see figure below).
For camera teams that have deep image quality tuning expertise, this significantly reduces the effort and uncertainty involved with subjective image quality requirements. But for teams with limited or even zero IQ tuning resources and expertise, NaturalIQ is said to provide a more intuitive method to differentiate their cameras and quickly respond to changing subjective requirements.
NaturalIQ is currently in initial trials with availability targeted for end 2018. Those interested in participating in those trials should contact Algolux. For more details, visit the company’s website.